Intelligent climate-responsive photovoltaic agricultural system for crop cultivation and intelligent control method thereof

Abstract

This invention relates to the interdisciplinary field of agricultural engineering and renewable energy integration, specifically disclosing an intelligent climate-responsive photovoltaic agricultural system (ICRAS) for crop cultivation and its intelligent control method. The system integrates biaxially adjustable semi-transparent bifacial photovoltaic modules, an IoT-based environmental and crop physiological sensor network, and a high-precision rainwater harvesting and drip irrigation mechanism. The AI ​​control unit employs an economic and biological weighted analysis method (EBWA) to adjust the orientation, transmittance, and irrigation rate of the photovoltaic modules in real time, achieving intelligent microclimate control. Mathematically, the EBWA algorithm sets the heat stress penalty coefficient as the dominant constraint, ensuring that crop protection and temperature regulation take precedence over energy output or economic benefits. This invention significantly improves crop productivity, water resource utilization efficiency, and photovoltaic power generation performance, providing a comprehensive solution for sustainable agriculture with scalability, adaptability, and climate resilience.

Description

Technical Field

[0001] This invention relates to the interdisciplinary field of agricultural engineering and renewable energy integration, and in particular to an intelligent climate-responsive photovoltaic agricultural system for crop cultivation and its intelligent control method. Background Technology

[0002] Perennial crops, such as tea and coffee plantations in subtropical and mountainous regions, are increasingly being adversely affected by climate change, including rising temperatures, irregular rainfall, and prolonged droughts. These climate stresses not only reduce crop yields and quality but also significantly increase irrigation demands.

[0003] Traditional shading methods, such as using shade trees or fixed photovoltaic panels, cannot flexibly cope with short-term climate fluctuations.

[0004] Existing global photovoltaic agricultural systems are mainly designed for annual crops, focusing on energy generation or static shading, but failing to precisely regulate the dynamic physiological needs of perennial, shade-loving crops such as tea and coffee, especially in sloping or terraced environments.

[0005] There is currently a lack of a solution in the technology that can prioritize crop safety in dynamic environments through a self-learning system, rather than simply pursuing energy output. Summary of the Invention

[0006] The purpose of this invention is to address the problems of existing technologies being unable to flexibly cope with short-term climate fluctuations and not covering the precise regulation of perennial crops and complex environments, and to optimize the coupling relationship between photovoltaic energy power generation and crop microclimate regulation.

[0007] To achieve the above objectives, the present invention provides an intelligent climate-responsive photovoltaic agricultural system for crop cultivation, comprising: photovoltaic modules, an Internet of Things sensor network, an adaptive irrigation subsystem, and a control unit; The number of photovoltaic modules is selected according to requirements and is installed on the support frame; The Internet of Things (IoT) sensor network includes at least one soil moisture sensor, at least one ambient temperature sensor, at least one relative humidity sensor, at least one solar radiation sensor, and at least one plant physiological parameter sensor, for measuring crop parameters. The adaptive irrigation subsystem includes a water storage tank that receives rainwater collected by the photovoltaic modules and distributes the stored rainwater to the crops. The control unit executes an artificial intelligence model, receives and processes data transmitted in real time from the Internet of Things sensor network, infers crop status and needs through a self-learning algorithm, and automatically generates control signals to adjust the orientation and light transmittance of photovoltaic modules and schedule irrigation.

[0008] Preferably, the communication protocol between the IoT sensor network and the control unit adopts LoRaWAN, NB-IoT, or 4G.

[0009] Preferably, the photovoltaic module adopts a semi-transparent double-sided photovoltaic panel, and the number of the support frame is adaptively adjusted according to the number of photovoltaic modules. The support frame is a dual-axis adjustable support frame, including a dual-axis tracking mechanism driven by a servo motor or a stepper motor, which can adjust the tilt angle from 0° to 60° and the azimuth angle from ±45° according to the control signal.

[0010] Preferably, the support frame adopts a modular design, uses corrosion-resistant materials, and its structure is adaptable to uneven terrain.

[0011] Preferably, the lower edge of the photovoltaic module is provided with an integrated rainwater collection channel, which is connected to a confluence channel fixed to the bottom of the support frame via a flexible connector. The confluence channel is connected to a water storage tank to guide rainwater to the water storage tank.

[0012] Preferably, the plant physiological parameter sensor includes at least one infrared thermal imaging sensor and at least one spectral sensor. The infrared thermal imaging sensor measures leaf surface temperature, and the spectral sensor calculates vegetation indices, including but not limited to the Normalized Difference Vegetation Index (NDVI) and the Light Reflectance Index (PRI).

[0013] Preferably, the adaptive irrigation subsystem further includes an intelligent drip irrigation network, which operates under the control of an artificial intelligence model, specifically as follows: Based on the evapotranspiration model, with water consumption penalty coefficient As dynamic control variables, the irrigation time and amount are determined by combining real-time air temperature, humidity, soil moisture content, leaf surface temperature and weather forecast.

[0014] Preferably, the water storage tank is equipped with a liquid level sensor and a filter module, and a water storage threshold is set in the control unit; The control unit compares the actual water storage volume measured by the liquid level sensor with the water storage threshold. When the actual water storage volume is greater than or equal to the water storage threshold, the control unit uses rainwater from the water storage tank for irrigation. When the actual water storage volume is less than the water storage threshold, the control unit activates an external water source for irrigation.

[0015] Preferably, the artificial intelligence model follows the EBWA model and defines a heat stress penalty term. As the primary constraint, The value is at least the highest positive reward factor. 20 times that of photovoltaic power, ensuring that crop thermal protection takes priority over photovoltaic output and economic benefits. This is the crop growth index.

[0016] Preferably, the control unit sets the leaf surface temperature of 30°C as the critical stress threshold. When the leaf surface temperature is ≥30°C in the data transmitted by the Internet of Things sensor network, the system ignores the current photovoltaic power generation output status and automatically starts photovoltaic module adjustment and irrigation adjustment.

[0017] Preferably, the orientation and light transmittance of the photovoltaic module are adjusted according to a dynamic shading coefficient, which is calculated based on solar irradiance, leaf temperature, and vegetation indices NDVI and PRI, so that the leaf temperature is maintained between 20°C and 28°C.

[0018] Preferably, the control unit is equipped with a digital twin module, which continuously mirrors the state of the planting environment by integrating physical models and data-driven models, simulating crop photosynthesis, transpiration and soil moisture dynamics, and realizing predictive simulation and optimized control.

[0019] Preferably, the control unit is based on a digital twin module to simulate short-term responses and selects the control strategy with the highest cumulative reward within the EBWA framework.

[0020] Preferably, the system also includes an energy-data management unit to coordinate the power and information flow within the system, including photovoltaic modules, batteries, pumps, sensors, and communication gateways; The energy-data management unit has built-in protection circuits, power flow optimization algorithms, and real-time monitoring functions to perform automatic fault detection, motor overload protection, and communication fault alarms.

[0021] Preferably, the energy-data management unit further includes maximum power point tracking (MPPT), intelligent load priority control, and automatic switching between photovoltaic and energy storage functions.

[0022] Preferably, the system also includes a cloud-based analysis platform, which is connected via a secure communication protocol to provide predictive maintenance alerts, production forecasts and remote monitoring functions, and adopts AES-256 encryption and a dual storage mechanism. The dual storage mechanism is that all system operating data is recorded locally and synchronized with the cloud platform.

[0023] Preferably, the system also includes a user interface, including a dashboard for web and mobile devices, displaying photovoltaic output, environmental parameters, irrigation status, and crop growth indicators.

[0024] Preferably, the user interface includes alarm and emergency shutdown functions, which issue alarms when abnormal conditions occur, including but not limited to overheating, communication interruption, and pump failure, and allow the user to stop the faulty part of the system based on the alarm in the user interface.

[0025] This invention also provides an intelligent control method for an intelligent climate-responsive photovoltaic agricultural system. The method, applying the aforementioned intelligent climate-responsive photovoltaic agricultural system for crop cultivation, includes the following steps: S1. Data Acquisition: Continuously collect environmental, soil and plant physiological data through the Internet of Things sensor network, including air temperature, humidity, solar radiation, soil moisture content and leaf surface temperature, and simultaneously collect multispectral vegetation indices, including NDVI and PRI. S2, AI Inference: A self-learning AI model, implemented using deep reinforcement learning (DRL) or hybrid predictive control (HMPC), processes the collected data to predict canopy stress and resource requirements. S3. Reward Function Calculation: Calculate the composite reward function based on the EBWA model. To ensure that crop physiological protection takes priority over economic and power generation goals; S4. Control Execution: Automatically adjust the tilt angle, azimuth angle, transmittance, and irrigation flow rate of photovoltaic modules based on the optimization results; S5. Feedback Learning: The weighted parameters are continuously updated through real-time plant status feedback.

[0026] The preferred EBWA model is as follows: Maximize the cumulative compound reward function Achieving a dynamic balance between energy output, crop health, and resource utilization efficiency through a composite reward function. The expression is: ; in, , , , These are adjustable weighting coefficients representing energy output, crop growth benefits, water resource costs, and heat stress penalties, respectively. The weighting coefficients , , , Follow hierarchical constraints: Set for 3-5 times, > , ≥ .

[0027] The present invention employs the above-mentioned intelligent climate-responsive photovoltaic agricultural system for crop cultivation and its intelligent control method, and the beneficial effects are as follows: (1) This invention adopts the Economic and Biological Weighted Analysis (EBWA) method to achieve intelligent control of microclimate by adjusting the orientation, transmittance and irrigation rate of photovoltaic modules in real time; (2) This invention uses the thermal stress penalty coefficient ( This is set as the dominant constraint to ensure that crop protection and temperature regulation take precedence over energy output or economic benefits. Every decision can maximize resource utilization efficiency while ensuring crop health and energy stability. (3) This invention significantly improves crop productivity, water resource utilization efficiency and photovoltaic power generation performance, providing a comprehensive solution for sustainable agriculture with scalability, adaptability and climate resilience. Attached Figure Description

[0028] Figure 1 This is a schematic diagram of the Intelligent Climate-Responsive Photovoltaic Agriculture System (ICRAS) of the present invention; Figure 2 This is a flowchart of the artificial intelligence control logic of the present invention; Figure 3 This is a three-dimensional conceptual layout diagram of the adaptive photovoltaic canopy arranged above terraced slopes according to the present invention. Figure 4 This is the control logic framework for the Economic and Biological Weighted Analysis (EBWA) of this invention. Detailed Implementation

[0029] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to specific embodiments and the accompanying drawings. It should be understood that these descriptions are merely exemplary and not intended to limit the scope of the invention. Furthermore, descriptions of well-known structures and techniques are omitted in the following description to avoid unnecessarily obscuring the concept of the invention.

[0030] I. For example Figure 1 As shown, the present invention discloses an intelligent climate-responsive photovoltaic agricultural system for crop cultivation, comprising: 1. Adaptive photovoltaic structure and flexible water collection mechanism: The photovoltaic modules use semi-transparent double-sided photovoltaic panels, the number of which can be selected according to the needs. They are installed on a dual-axis adjustable support frame with a dual-axis tracking mechanism driven by a high-precision servo motor or stepper motor. Each support frame can be adjusted in tilt angle from 0° to 60° and azimuth angle from ±45° according to the control signal. This allows the system to maintain stability on slopes or terraces while having sufficient angular freedom to adapt to changes in the solar trajectory during the day and night and seasonally.

[0031] The support frame employs a modular design and corrosion-resistant materials, and its structure is optimized for uneven terrain to ensure long-term durability and hydrological performance stability under dynamic operating conditions. Modular supports, such as... Figure 3 As shown.

[0032] An integrated rainwater collection channel is located at the lower edge of the photovoltaic module, connected to a catchment trough fixed to the bottom of the support frame via flexible connectors (including telescopic corrugated pipes). This flexible connection design ensures smooth drainage and reliable sealing throughout the entire tracking range, enabling uninterrupted rainwater collection regardless of the module's orientation. The catchment trough connects to a water storage tank, guiding rainwater there for subsequent precision irrigation.

[0033] 2. Internet of Things (IoT) sensor network: including at least one soil moisture sensor, at least one ambient temperature sensor, at least one relative humidity sensor, at least one solar radiation sensor, and at least one plant physiological parameter sensor, for measuring crop parameters. The plant physiological parameter sensor includes at least one infrared thermal imaging sensor and at least one spectral sensor.

[0034] The IoT network collects data from three levels: (1) the macro-environment layer, including routine meteorological data such as ambient temperature, humidity, solar radiation, and wind speed; (2) the micro-environment layer, monitoring soil moisture content and pH at different soil depths, as well as local air temperature and humidity around the crop canopy; and (3) the physiological layer, acquiring key data through crop physiological parameter sensors, including measuring leaf surface temperature (LST) using infrared thermal imaging, and calculating the normalized difference vegetation index (NDVI) and photochemical reflectance index (PRI) using multispectral or hyperspectral sensors. LST is a key input for assessing heat stress, while NDVI / PRI is used to calculate crop growth indices (…). ).

[0035] 3. Water collection and adaptive irrigation subsystem, such as Figure 3 As shown: It includes a water storage tank, an integrated drainage pipe and a flexible joint, which can continuously guide the rainwater collected by the photovoltaic modules into the water storage tank at any tilt angle or orientation, and distribute the stored rainwater to the crops.

[0036] The water storage tank is equipped with a liquid level sensor and a filter module. A water storage threshold is set in the control unit. The actual water storage volume measured by the liquid level sensor is compared with the water storage threshold. When the actual water storage volume is greater than or equal to the water storage threshold, the control unit uses the rainwater in the water storage tank for irrigation. When the actual water storage volume is less than the water storage threshold, the control unit uses an external water source for irrigation.

[0037] The intelligent drip irrigation network operates under real-time feedback control of AI algorithms, based on an evapotranspiration model and a water consumption penalty coefficient. As a dynamic control variable, the system combines real-time air temperature, humidity, soil moisture content, leaf surface temperature, and weather forecasts to comprehensively analyze and determine irrigation time and amount. Irrigation is triggered when high irrigation efficiency is indicated. This strategy maximizes irrigation efficiency, prevents ineffective water loss, and promotes rainwater reuse, thereby maintaining long-term resource conservation and crop canopy microclimate stability.

[0038] 4. Control Unit: Executes an artificial intelligence model, receives and processes real-time data transmitted from the IoT sensor network, infers crop status and needs through self-learning algorithms, and automatically generates control signals to adjust the orientation and light transmittance of photovoltaic modules and schedule irrigation. The communication protocol between the IoT sensor network and the control unit adopts LoRaWAN, NB-IoT, or 4G.

[0039] Artificial intelligence control algorithms—EBWA method (e.g.) Figure 4 The integration (as shown) involves an artificial intelligence (AI) control system implemented using deep reinforcement learning (DRL) or a hybrid model predictive control (HMPC) framework to solve the dynamic optimization problem defined by the EBWA method, specifically: The main goal of AI models is to maximize the cumulative reward function. Achieving a dynamic balance between energy output, crop health, and resource utilization efficiency is mathematically expressed as: ; Among them: photovoltaic power generation ( Item): Represents the instantaneous or periodic power generation of photovoltaic modules, which has a positive effect on the total reward; Crop growth index (CGI) Item: This is a dimensionless predictive index, calculated from multispectral vegetation indices such as NDVI and PRI. It is significantly correlated with biomass accumulation and yield potential, and is a real-time indicator reflecting crop physiological performance. Water consumption ( Item): Represents the total irrigation water consumption within the control period, assigned a negative weight to encourage water conservation and rainwater reuse; Heat stress penalty item ( (Item): Quantifies the degree to which leaf surface temperature deviates from the optimal physiological range of 20°C–28°C. When the leaf temperature exceeds approximately 30°C, the penalty value increases sharply, triggering the system to immediately implement corrective measures such as increasing shading or micro-irrigation for cooling, regardless of the current photovoltaic power generation output status; , , , Adjustable weighted coefficients representing energy output, crop growth benefits, water resource costs, and heat stress penalties are used to define optimization priorities. These coefficients are calculated using the EBWA method, transforming economic parameters and biological constraints into utility functions for the AI ​​agent.

[0040] Within the EBWA framework, the weighting coefficients follow a strict hierarchical structure: Economic weighted ( relatively Crop growth reward ( ) is set as a photovoltaic power generation reward ( The value of perennial cash crops is 3–5 times that of energy output, to reflect the long-term economic value of perennial cash crops relative to energy output, thereby ensuring that AI decision-making prioritizes crop productivity and quality rather than short-term maximum power generation revenue. Resource efficiency ( relatively Water consumption penalty ( ) Set higher than the power generation reward ( This forces the control system to treat water resources as a high-cost variable, promoting water conservation and rainwater recycling; Absolute biological constraints ( Heat stress punishment ( The coefficient is fixed at no less than the highest positive reward coefficient. 20 times () ≥20× This extremely high weight constitutes an inviolable mathematical constraint, forcing the AI ​​to choose only control strategies that can prevent or mitigate thermal stress, even if this temporarily reduces power generation or growth rewards.

[0041] The AI ​​model continuously infers plant stress status through infrared thermal imaging and multispectral sensors. When it detects an increase in leaf temperature and a decrease in PRI (indicating photoinhibition or heat stress), the controller will automatically adjust the angle of the photovoltaic modules to increase shading and activate a precision micro-irrigation or spray system, thereby restoring the canopy temperature to the optimal range of 20°C–28°C, protecting the crop's photosynthetic system, and achieving sustainable and stable yields. The automatic adjustment of photovoltaic module shading is based on a dynamic shading coefficient, which is calculated based on solar irradiance, leaf surface temperature, and vegetation indices NDVI and PRI.

[0042] 5. Energy-Data Management Unit: Coordinates all power and information flows within the system, including photovoltaic modules, batteries, pumps, sensors, and communication gateways; features built-in protection circuits, power flow optimization algorithms, and real-time monitoring functions for automatic fault detection, motor overload protection, and communication fault alarms.

[0043] The system achieves dynamic balance between energy supply and demand through maximum power point tracking (MPPT), intelligent load priority control, and automatic switching (photovoltaic / energy storage).

[0044] 6. Cloud Platform: A cloud-based analytics platform that connects via secure communication protocols to provide predictive maintenance alerts, production forecasts, and remote monitoring capabilities; The system adopts AES-256 encryption and a dual storage mechanism. The dual storage mechanism is as follows: all system operation data is recorded and analyzed locally and synchronized with the cloud platform for long-term performance analysis, predictive diagnosis and system optimization.

[0045] 7. User Interface: The system provides real-time visualization through web-based and mobile dashboards, displaying photovoltaic output, environmental parameters, irrigation status, and crop growth indicators; users can perform manual intervention, predictive maintenance scheduling, and yield analysis.

[0046] It also includes alarm and emergency shutdown functions, which issue alarms when abnormal conditions such as overheating, communication interruption, or pump failure occur. Users can stop the faulty part of the system based on the alarm in the user interface to support proactive maintenance and stable system operation.

[0047] 8. Digital Twin Module: The control unit is equipped with a digital twin model to reproduce the hybrid simulation state of the planting environment. It combines the physical model with the data-driven model to simulate microclimate, crop photosynthesis, evapotranspiration and soil moisture dynamics and crop physiological responses in real time, so as to achieve predictive simulation and optimized control.

[0048] Before executing any control action, the AI ​​controller simulates short-term system behavior (typically a 30-minute prediction window) using a digital twin to assess the expected impact on temperature, soil moisture content, and photovoltaic energy balance. By selecting the control strategy with the highest cumulative reward within the EBWA framework, the digital twin achieves predictive optimization, ensuring that every decision made by the controller maximizes resource utilization efficiency while safeguarding crop health and energy stability.

[0049] II. The present invention discloses an intelligent control method for a smart climate-responsive photovoltaic agricultural system, the control logic of which is as follows: Figure 2 As shown, it includes the following steps: S1. Data Acquisition: Continuously collect environmental, soil and plant physiological data through the Internet of Things sensor network, including air temperature, humidity, solar radiation, soil moisture content and leaf surface temperature, and simultaneously collect multispectral vegetation indices, including NDVI and PRI. S2, AI Inference: A self-learning AI model, implemented using deep reinforcement learning (DRL) or hybrid predictive control (HMPC), processes the collected data to predict canopy stress and resource requirements. S3. Reward Function Calculation: Calculate the composite reward function based on the EBWA model. To ensure that crop physiological protection takes priority over economic and power generation goals; S4. Control Execution: Automatically adjust the tilt angle, azimuth angle, transmittance, and irrigation flow rate of photovoltaic modules based on the optimization results; S5. Feedback Learning: The weighted parameters are continuously updated through real-time plant status feedback.

[0050] Therefore, this invention employs the aforementioned intelligent climate-responsive photovoltaic agricultural system and its intelligent control method for crop cultivation. Using the Economic and Biological Weighted Analysis (EBWA) method, it achieves intelligent microclimate regulation by real-time adjustment of the photovoltaic module's orientation, transmittance, and irrigation rate. This invention incorporates a heat stress penalty coefficient (…). This is set as the dominant constraint, ensuring that crop protection and temperature regulation take precedence over energy output or economic benefits. Every decision can maximize resource utilization efficiency while ensuring crop health and energy stability. It significantly improves crop productivity, water resource utilization efficiency and photovoltaic power generation performance, providing a comprehensive solution for sustainable agriculture with scalability, adaptability and climate resilience.

[0051] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can still be made to the technical solutions of the present invention, and these modifications or equivalent substitutions cannot cause the modified technical solutions to deviate from the spirit and scope of the technical solutions of the present invention.

Claims

1. A smart climate-responsive photovoltaic agricultural system for crop cultivation, characterized in that, include: Photovoltaic modules, Internet of Things sensor network, adaptive irrigation subsystem, control unit; The number of photovoltaic modules is selected according to requirements and is installed on the support frame; The Internet of Things (IoT) sensor network includes at least one soil moisture sensor, at least one ambient temperature sensor, at least one relative humidity sensor, at least one solar radiation sensor, and at least one plant physiological parameter sensor, for measuring crop parameters. The adaptive irrigation subsystem includes a water storage tank that receives rainwater collected by the photovoltaic modules and distributes the stored rainwater to the crops. The control unit executes an artificial intelligence model, receives and processes data transmitted in real time from the Internet of Things sensor network, infers crop status and needs through a self-learning algorithm, and automatically generates control signals to adjust the orientation and light transmittance of photovoltaic modules and schedule irrigation.

2. The intelligent climate-responsive photovoltaic agricultural system for crop cultivation according to claim 1, characterized in that, The communication protocol between the IoT sensor network and the control unit adopts LoRaWAN, NB-IoT or 4G.

3. The intelligent climate-responsive photovoltaic agricultural system for crop cultivation according to claim 1, characterized in that, The photovoltaic module adopts a semi-transparent double-sided photovoltaic panel. The number of the support frame is adaptively adjusted according to the number of photovoltaic modules. The support frame is a dual-axis adjustable support frame, including a dual-axis tracking mechanism driven by a servo motor or stepper motor, which can adjust the tilt angle from 0° to 60° and the azimuth angle from ±45° according to the control signal.

4. The intelligent climate-responsive photovoltaic agricultural system for crop cultivation according to claim 1, characterized in that, The support frame adopts a modular design, uses corrosion-resistant materials, and its structure is adaptable to uneven terrain.

5. The intelligent climate-responsive photovoltaic agricultural system for crop cultivation according to claim 1, characterized in that, An integrated rainwater collection channel is provided at the lower edge of the photovoltaic module. The rainwater collection channel is connected to a confluence channel fixed to the bottom of the support frame through a flexible connector. The confluence channel is connected to a water storage tank to guide rainwater to the water storage tank.

6. The intelligent climate-responsive photovoltaic agricultural system for crop cultivation according to claim 1, characterized in that, The plant physiological parameter sensor includes at least one infrared thermal imaging sensor and at least one spectral sensor. The infrared thermal imaging sensor measures leaf surface temperature, and the spectral sensor calculates vegetation indices, including but not limited to the Normalized Difference Vegetation Index (NDVI) and the Light Reflectance Index (PRI).

7. The intelligent climate-responsive photovoltaic agricultural system for crop cultivation according to claim 1, characterized in that, The adaptive irrigation subsystem also includes an intelligent drip irrigation network, which operates under the control of an artificial intelligence model, specifically as follows: Based on the evapotranspiration model, with water consumption penalty coefficient As dynamic control variables, the irrigation time and amount are determined by combining real-time air temperature, humidity, soil moisture content, leaf surface temperature and weather forecast.

8. The intelligent climate-responsive photovoltaic agricultural system for crop cultivation according to claim 1, characterized in that, The water storage tank is equipped with a liquid level sensor and a filter module, and a water storage threshold is set in the control unit. The control unit compares the actual water storage volume measured by the liquid level sensor with the water storage threshold. When the actual water storage volume is greater than or equal to the water storage threshold, the control unit uses rainwater from the water storage tank for irrigation. When the actual water storage volume is less than the water storage threshold, the control unit activates an external water source for irrigation.

9. The intelligent climate-responsive photovoltaic agricultural system for crop cultivation according to claim 1, characterized in that, The artificial intelligence model follows the EBWA model and defines a heat stress penalty term. As the primary constraint, The value is at least the highest positive reward factor. 20 times that of photovoltaic power, ensuring that crop thermal protection takes priority over photovoltaic output and economic benefits. This is the crop growth index.

10. The intelligent climate-responsive photovoltaic agricultural system for crop cultivation according to claim 1, characterized in that, The control unit sets the leaf surface temperature of 30°C as the critical stress threshold. When the leaf surface temperature is ≥30°C in the data transmitted by the Internet of Things sensor network, the system ignores the current photovoltaic power generation output status and automatically starts the photovoltaic module adjustment and irrigation adjustment.

11. A smart climate-responsive photovoltaic agricultural system for crop cultivation according to any one of claims 1 or 10, characterized in that, The orientation and light transmittance of the photovoltaic modules are adjusted according to a dynamic shading coefficient, which is calculated based on solar irradiance, leaf temperature, and vegetation indices NDVI and PRI, so that the leaf temperature is maintained between 20°C and 28°C.

12. The intelligent climate-responsive photovoltaic agricultural system for crop cultivation according to claim 9, characterized in that, The control unit is equipped with a digital twin module, which continuously mirrors the state of the planting environment by integrating physical models and data-driven models, simulating crop photosynthesis, transpiration and soil moisture dynamics, and realizing predictive simulation and optimized control.

13. The intelligent climate-responsive photovoltaic agricultural system for crop cultivation according to claim 12, characterized in that, The control unit is based on a digital twin module to simulate short-term responses and selects the control strategy with the highest cumulative reward within the EBWA framework.

14. The intelligent climate-responsive photovoltaic agricultural system for crop cultivation according to claim 1, characterized in that, The system also includes an energy-data management unit that coordinates the flow of power and information within the system, including photovoltaic modules, batteries, pumps, sensors, and communication gateways. The energy-data management unit has built-in protection circuits, power flow optimization algorithms, and real-time monitoring functions to perform automatic fault detection, motor overload protection, and communication fault alarms.

15. The intelligent climate-responsive photovoltaic agricultural system for crop cultivation according to claim 14, characterized in that, The energy-data management unit also includes maximum power point tracking (MPPT), intelligent load priority control, and automatic switching between photovoltaic and energy storage functions.

16. The intelligent climate-responsive photovoltaic agricultural system for crop cultivation according to claim 1, characterized in that, The system also includes a cloud-based analytics platform that connects via a secure communication protocol to provide predictive maintenance alerts, production forecasts, and remote monitoring. It employs AES-256 encryption and a dual-layer storage mechanism, whereby all system operating data is recorded locally and synchronized with the cloud platform.

17. The intelligent climate-responsive photovoltaic agricultural system for crop cultivation according to claim 1, characterized in that, The system also includes a user interface, including dashboards for web and mobile devices, which display photovoltaic output, environmental parameters, irrigation status, and crop growth indicators.

18. The intelligent climate-responsive photovoltaic agricultural system for crop cultivation according to claim 17, characterized in that, The user interface includes alarm and emergency shutdown functions. When abnormal conditions occur, including but not limited to overheating, communication interruption, and pump failure, an alarm is issued. The user can then stop the faulty part of the system based on the alarm in the user interface.

19. A smart control method for a smart climate-responsive photovoltaic agricultural system, employing the smart climate-responsive photovoltaic agricultural system for crop cultivation as described in any one of claims 1-18, characterized in that, Includes the following steps: S1. Data Acquisition: Continuously collect environmental, soil and plant physiological data through the Internet of Things sensor network, including air temperature, humidity, solar radiation, soil moisture content and leaf surface temperature, and simultaneously collect multispectral vegetation indices, including NDVI and PRI. S2, AI Inference: A self-learning AI model, implemented using deep reinforcement learning (DRL) or hybrid predictive control (HMPC), processes the collected data to predict canopy stress and resource requirements. S3. Reward Function Calculation: Calculate the composite reward function based on the EBWA model. To ensure that crop physiological protection takes priority over economic and power generation goals; S4. Control Execution: Automatically adjust the tilt angle, azimuth angle, transmittance, and irrigation flow rate of photovoltaic modules based on the optimization results; S5. Feedback Learning: The weighted parameters are continuously updated through real-time plant status feedback.

20. The intelligent control method for an intelligent climate-responsive photovoltaic agricultural system according to claim 19, characterized in that, The EBWA model is as follows: Maximize the cumulative compound reward function Achieving a dynamic balance between energy output, crop health, and resource utilization efficiency through a composite reward function. The expression is: ； in, , , , These are adjustable weighting coefficients representing energy output, crop growth benefits, water resource costs, and heat stress penalties, respectively. The weighting coefficients , , , Follow hierarchical constraints: Set for 3-5 times, > , ≥ .

Images